Enterprise technology achievement evaluation method, device, equipment and medium

Abstract

The invention discloses an enterprise technology achievement evaluation method and device, equipment and a medium, and relates to the technical field of computers. Comprising the steps of obtaining multi-source data including technical dimension data and market dimension data and related to a target enterprise technical achievement; performing feature fusion operation on the technical dimension data and the market dimension data by using a preset space-time alignment engine and a preset semantic alignment engine to obtain a fused feature vector; constructing a technical node and a market node based on the fusion feature vector, and constructing a dynamic association network map based on the technical node and the market node by using a cross-domain attention network created based on a bidirectional attention mechanism; and analyzing the dynamic association network atlas by using a preset deep learning algorithm to obtain a target analysis result corresponding to the target enterprise technical achievement. Therefore, the problems of data splitting, dynamic deficiency and cross-domain association insufficiency can be solved, and joint intelligent prediction of technology maturity and market suitability is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a technology achievement evaluation method and device of enterprise, equipment and medium. BACKGROUND

[0002] Technology readiness level (TRL) is a standard for measuring and evaluating the maturity of technology. At present, there are the following problems in the evaluation of technology maturity and market adaptability of technology achievements in the process of transformation to the market: technology evaluation and market evaluation are usually independent of each other, and there is a lack of effective cross-domain data correlation and comprehensive analysis method. Traditional technology maturity evaluation methods often focus only on technology indicators in the research and development stage, and fail to fully incorporate market demand dynamics for feedback adjustment. Existing evaluation models are mostly static models, which are difficult to capture and respond to sudden changes in the technology evolution process and dramatic fluctuations in the market environment such as sudden adjustments in policies and regulations. Traditional regression models that rely on historical data have high prediction error rates when evaluating emerging technology fields, making it difficult to adapt to rapidly changing environments. Existing correlation technologies such as knowledge graphs are mainly applied in a single field, and lack a mechanism for establishing deep and effective correlations between technology and market fields.

[0003] From the above, how to solve the problems of data fragmentation, lack of dynamics and insufficient cross-domain correlation, and realize the joint intelligent prediction of technology maturity and market adaptability is an urgent problem to be solved. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a technology achievement evaluation method and device of enterprise, equipment and medium, which can solve the problems of data fragmentation, lack of dynamics and insufficient cross-domain correlation, and realize the joint intelligent prediction of technology maturity and market adaptability. The specific solutions are as follows:

[0005] In a first aspect, the present application provides a technology achievement evaluation method of enterprise, comprising: obtaining multi-source data related to the target technology achievement of enterprise, including technology dimension data and market dimension data; performing feature fusion operation on the technology dimension data and the market dimension data by using a preset spatio-temporal alignment engine and a preset semantic alignment engine to obtain a fusion feature vector; the technology dimension data includes patent data, paper data and research and development data; the market dimension data includes user behavior data, industry report data and competitive intelligence data; the fusion feature vector includes a technology feature vector and a market feature vector; Constructing technology nodes and market nodes based on the fused feature vector, and utilizing a cross-domain attention network created based on a bidirectional attention mechanism, and constructing a dynamic association network graph based on the technology nodes and the market nodes; the dynamic association network graph is a graph that characterizes the association between the technology nodes and the market nodes; The dynamic association network map is analyzed using a preset deep learning algorithm to obtain target analysis results corresponding to the target enterprise's technological achievements; the target analysis results include technology maturity level, market adaptation index and coordination risk probability.

[0006] Optionally, the using a preset spatiotemporal alignment engine and a preset semantic alignment engine to perform a feature fusion operation on the technical dimension data and the market dimension data to obtain a fused feature vector includes: Utilizing the preset spatiotemporal alignment engine to design a mapping benchmark offset rule for the technology stage to the market window period based on a dynamic offset mechanism; Utilizing the preset spatiotemporal alignment engine to generate a dynamic offset related to the strength of the technological breakthrough based on a preset compensation algorithm, and mapping the technology dimension data and the market dimension data onto a unified timeline based on the mapping benchmark offset rule and the dynamic offset, so as to obtain the technology dimension data and the market dimension data after spatiotemporal alignment; The preset semantic alignment engine is used to perform feature fusion operation on the technical dimension data and the market dimension data after the spatiotemporal alignment in a two-way vectorization manner to obtain a fused feature vector.

[0007] Optionally, constructing a technology node and a market node based on the fused feature vector includes: Deepening the technical feature vector based on the international patent classification tree to obtain a technical node; The market characteristic vector is expanded based on the industrial chain to obtain a market node.

[0008] Optionally, the cross-domain attention network created based on the bidirectional attention mechanism is used to construct a dynamic association network graph based on the technology nodes and the market nodes, including: Using a cross-domain attention network created based on a bidirectional attention mechanism, a first correlation relationship representing the contribution of technology to the market and a second correlation relationship representing the market's influence on technology are established based on the technology node and the market node, and a first correlation strength of the first correlation relationship and a second correlation strength of the second correlation relationship are calculated using a preset bidirectional attention mechanism; A dynamic association network graph is constructed based on the first association relationship, the second association relationship, the technology node, and the market node.

[0009] Optionally, after utilizing the cross-domain attention network created based on the bidirectional attention mechanism and constructing a dynamic association network graph based on the technology nodes and the market nodes, the method further includes: Based on the preset dynamic maintenance strategy, technical nodes and market nodes whose correlation closeness is lower than the preset strength threshold or the change amplitude of the correlation closeness within the preset time is greater than the preset change threshold are eliminated to complete the optimization of the dynamic correlation network map; the value of the correlation closeness is the value obtained by the geometric average of the first correlation strength and the second correlation strength.

[0010] Optionally, the analyzing the dynamic association network graph using a preset deep learning algorithm to obtain a target analysis result corresponding to the target enterprise's technological achievements includes: Obtaining market volatility monitoring data, and adjusting assessment weight parameters based on the market volatility monitoring data; The dynamic association network map is analyzed using a preset deep learning algorithm based on the adjusted evaluation weight parameters to obtain the target analysis results corresponding to the target enterprise's technological achievements.

[0011] Optionally, the enterprise technological achievement evaluation method further includes: The preset deep learning algorithm is updated based on a dual-loop dynamic update mechanism; the dual-loop dynamic update mechanism includes a target short-term loop update and a target long-term loop update, the target short-term loop update is a model update operation triggered by a market fluctuation event; the target long-term loop update is a model update operation triggered by a technological breakthrough event.

[0012] In a second aspect, the present application provides an enterprise technology achievement evaluation device, comprising: A data acquisition module is used to acquire multi-source data related to the target enterprise's technological achievements, including technical dimension data and market dimension data; a feature fusion module, configured to perform a feature fusion operation on the technical dimension data and the market dimension data using a preset spatiotemporal alignment engine and a preset semantic alignment engine to obtain a fused feature vector; the technical dimension data includes patent data, paper data, and R&D data; the market dimension data includes user behavior data, industry report data, and competitive intelligence data; and the fused feature vector includes a technical feature vector and a market feature vector; A graph construction module is configured to construct technology nodes and market nodes based on the fused feature vector, and to utilize a cross-domain attention network created based on a bidirectional attention mechanism to construct a dynamic association network graph based on the technology nodes and the market nodes; the dynamic association network graph is a graph that characterizes the association between the technology nodes and the market nodes; A result generation module is used to analyze the dynamic association network map using a preset deep learning algorithm to obtain target analysis results corresponding to the target enterprise's technological achievements; the target analysis results include technology maturity level, market adaptation index and coordination risk probability.

[0013] In a third aspect, the present application provides an electronic device, comprising: Memory, used to store computer programs; The processor is used to execute the computer program to implement the aforementioned enterprise technology achievement evaluation method.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, wherein the computer program implements the aforementioned enterprise technological achievement evaluation method when executed by a processor.

[0015] The present application provides a method for evaluating enterprise technological achievements. First, multi-source data including technology dimension data and market dimension data related to the target enterprise technological achievements is obtained, and a preset spatiotemporal alignment engine and a preset semantic alignment engine are used to perform feature fusion operations on the technology dimension data and the market dimension data to obtain a fused feature vector; the technology dimension data includes patent data, paper data and R&D data; the market dimension data includes user behavior data, industry report data and competitive intelligence data; the fused feature vector includes a technology feature vector and a market feature vector; then, technology nodes and market nodes are constructed based on the fused feature vector, and a cross-domain attention network created based on a bidirectional attention mechanism is used to construct a dynamic association network map based on the technology nodes and the market nodes; finally, a preset deep learning algorithm is used to analyze the dynamic association network map to obtain a target analysis result corresponding to the target enterprise technological achievements; the target analysis result includes a technology maturity level, a market adaptation index and a coordination risk probability.

[0016] As can be seen from the above, this application performs feature fusion operations on the technical dimension data and the market dimension data through a preset spatiotemporal alignment engine and a preset semantic alignment engine, establishes a dynamic alignment mechanism for technical features and market features, and eliminates data fragmentation; utilizes a cross-domain attention network created based on a bidirectional attention mechanism, and constructs a dynamic association network map based on the technical nodes and the market nodes to capture the implicit association between technological evolution and market demand; uses a preset deep learning algorithm to analyze the dynamic association network map to achieve joint intelligent prediction of technology maturity and market adaptability. This can solve data fragmentation, lack of dynamism, and insufficient cross-domain association, and achieve joint intelligent prediction of technology maturity and market adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0018] Figure 1 A flow chart of a method for evaluating enterprise technological achievements disclosed in this application; Figure 2 This is a flow chart of a feature fusion architecture disclosed in this application; Figure 3 A flowchart of a graph construction architecture disclosed in this application; Figure 4 This is a flow chart of an intelligent assessment architecture disclosed in this application; Figure 5 A schematic diagram of an enterprise technology achievement evaluation device disclosed in this application; Figure 6 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] Technology maturity measures the extent to which key technologies meet project objectives and is a key factor in project risk. The technology maturity level is a standard for measuring and evaluating technology maturity. Currently, the assessment of technology maturity and market adaptability during the market transition of scientific and technological achievements faces the following challenges: technology and market evaluations are often conducted independently, lacking effective cross-domain data correlation and comprehensive analysis methods. Traditional technology maturity assessment methods often focus solely on technical indicators during the R&D phase and fail to fully incorporate dynamic market demand for feedback and adjustment. Existing assessment models are mostly static, making it difficult to capture and respond in real time to sudden changes in technological evolution and drastic market fluctuations, such as sudden adjustments to policies and regulations. Traditional regression models that rely on historical data have high prediction errors when evaluating emerging technology areas and are unable to adapt to rapidly changing environments. Existing correlation technologies, such as knowledge graphs, are primarily applied to single domains and lack mechanisms for establishing deep and effective correlations between technology and market. To address this issue, this application provides an enterprise technology achievement assessment solution that addresses data fragmentation, lack of dynamism, and insufficient cross-domain correlation, enabling joint intelligent prediction of technology maturity and market adaptability.

[0021] See also Figure 1 As shown, the embodiment of the present application discloses a method for evaluating enterprise technological achievements, including:

[0022] Step S11: Acquire multi-source data related to the target enterprise's technological achievements, including technology dimension data and market dimension data.

[0023] In this embodiment, the technical dimension data includes but is not limited to patent data, paper data, and R&D data; the market dimension data includes but is not limited to user behavior data, industry report data, and competitive intelligence data. Multi-source data is collected from technical dimensions such as patents, papers, and R&D data, and market dimensions such as user behavior, industry reports, and competitive intelligence. Through mapping, the dynamic shift between technology stages and market windows is correlated. Furthermore, semantic alignment of patent terms with market concepts is achieved to resolve data fragmentation.

[0024] Step S12: Using a preset spatiotemporal alignment engine and a preset semantic alignment engine, a feature fusion operation is performed on the technical dimension data and the market dimension data to obtain a fused feature vector.

[0025] See also Figure 2As shown, the embodiment adopts a space-time alignment engine and a semantic alignment engine to solve the space-time and semantic gap between technical data and market data. The fusion feature vector includes a technical feature vector and a market feature vector. Specifically, the feature fusion operation on the technical dimension data and the market dimension data by using the preset space-time alignment engine and the preset semantic alignment engine to obtain the fusion feature vector can include: using the preset space-time alignment engine to design a mapping reference offset rule for the technical stage to the market window period based on a dynamic offset mechanism; using the preset space-time alignment engine to generate a dynamic offset amount related to the technical breakthrough strength based on a preset compensation algorithm, and mapping the technical dimension data and the market dimension data onto a unified timeline based on the mapping reference offset rule and the dynamic offset amount to obtain the space-time aligned technical dimension data and market dimension data; using the preset semantic alignment engine to perform feature fusion operation on the space-time aligned technical dimension data and market dimension data in a double-path vectorization manner to obtain the fusion feature vector. That is, the dynamic offset mechanism is adopted, the mapping reference offset rule for the preset technical stage to the market window period is adopted, the preset compensation algorithm is adopted, and the offset amount is dynamically compressed according to the technical breakthrough strength. For example, when the battery energy density breaks through 400Wh / kg, which is a major technical breakthrough, the offset period of the market concept verification is shortened. By the above-mentioned manner, the technical event and the market event can be mapped onto a unified timeline. The technical terms and market concepts are vectorized in a double-path vectorization manner. In terms of technical terms, the IPC (International Patent Classification) is embedded in layers for vectorization, such as H01M10 / 0562, which can be divided into H (part) electricity, H01 (large category) basic electrical elements, H01M (small category) battery, H01M10 (large group) secondary battery, H01M10 / 0562 (small group) solid-state electrolyte lithium battery, and further coded as a 128-dimensional vector. In terms of market concepts, an industry corpus can be constructed first, and then a BERT (Bidirectional Encoder Representations from Transformers) model can be fine-tuned. The industry corpus is vectorized by BERT, and market demand is coded as a 768-dimensional vector. Thus, a dynamic alignment mechanism of technical features and market features is established, and data fragmentation is eliminated.

[0026] Step S13, based on the fusion feature vector, construct a technical node and a market node, and use a cross-domain attention network created based on a bidirectional attention mechanism, and based on the technical node and the market node, construct a dynamic association network graph.

[0027] In this embodiment, based on feature fusion, technology nodes and market nodes are constructed through a cross-domain attention network. Specifically, constructing technology nodes and market nodes based on the fused feature vector may include: deepening the technology feature vector based on the international patent classification tree to obtain the technology node; and expanding the market feature vector based on the industry chain to obtain the market node. In other words, the technology node can be split vertically along the IPC classification tree into four levels of subgroups, and then gradually deepened. For example, the node deepening for solid-state batteries is: H01M (battery) - H01M10 (secondary battery) - H01M10 / 0562 (solid-state electrolyte). The market node can be extended horizontally along the industry chain to three levels of entities, such as lithium ore supplier - battery material factory - new energy vehicle manufacturer.

[0028] Furthermore, an association relationship is established, a dynamically evolving technology-market association network is constructed, and implicit relationships are captured. Specifically, the cross-domain attention network created based on the two-way attention mechanism is used, and a dynamic association network map is constructed based on the technology nodes and the market nodes. This can include: using a cross-domain attention network created based on the two-way attention mechanism, and establishing a first association relationship that characterizes the contribution of technology to the market and a second association relationship that characterizes the market's traction to technology based on the technology nodes and the market nodes, and using a preset two-way attention mechanism to calculate the first association strength of the first association relationship and the second association strength of the second association relationship; constructing a dynamic association network map based on the first association relationship, the second association relationship, the technology nodes, and the market nodes. That is, by replacing the traditional static association with the two-way attention mechanism, the association strength of the two parts of technology contribution to the market and market traction to technology is calculated, and the interaction between the technology market is quantified in real time. Among them, the contribution of technology to the market, that is, the promotion of market hotspots by computing technology breakthroughs, can be calculated by patent growth rate and market attention. The specific formula is as follows:

[0029] ;

[0030] in, The correlation strength of technology's contribution to the market. The market's traction on technology is to assess the traction strength of demand changes on the technology path. It can be calculated by the demand change rate and the technology maturity change rate. The specific formula is as follows:

[0031] ;

[0032] in, is the strength of the correlation between the market and the technology's traction; is the demand change rate, which is used to indicate the market expansion speed; is the rate of change of technology maturity, which is used to indicate the speed of technology evolution. The number of correlation pairs with market-to-technology traction in the current calculation period.

[0033] Furthermore, this embodiment filters out weakly associated nodes through dynamic maintenance, and uses weight decay to update weights for intelligent pruning. Specifically, after the cross-domain attention network created based on the bidirectional attention mechanism is used and a dynamic associated network map is constructed based on the technical nodes and the market nodes, it may also include: based on a preset dynamic maintenance strategy, the technical nodes and market nodes whose association closeness is lower than a preset strength threshold or whose change in the association closeness within a preset time is greater than a preset change threshold are eliminated to complete the optimization of the dynamic associated network map; the value of the association closeness is the geometric average of the first association strength and the second association strength. That is, remove weakly associated nodes with low coupling strength or excessively high monthly activity drop. Further reduce the complexity of the calculation and improve the recognition accuracy of key relationships.

[0034] Step S14: Analyze the dynamic association network graph using a preset deep learning algorithm to obtain target analysis results corresponding to the target enterprise's technological achievements.

[0035] In this embodiment, the constructed knowledge graph features are dynamically analyzed by a deep learning algorithm to obtain the target analysis results. The target analysis results include the technology maturity level, market adaptation index and coordination risk probability. Figure 4 As shown, in a specific embodiment, a multi-task Transformer model extracts cross-domain features through a shared encoder, and dynamically adjusts the weights to collaboratively output three indicators of intelligent evaluation. At the same time, in view of the rapid changes in the market and the complex influencing factors, the market node update data is integrated in real time, the evaluation weight parameters are dynamically adjusted, and the intelligent judgment of technology value evaluation and market prospect forecast is jointly output. Specifically, the use of a preset deep learning algorithm to analyze the dynamic association network map to obtain the target analysis results corresponding to the target enterprise's technological achievements can include: obtaining market volatility monitoring data and adjusting the evaluation weight parameters based on the market volatility monitoring data; using a multi-task Transformer model to analyze the dynamic association network map based on the adjusted evaluation weight parameters to obtain the target analysis results corresponding to the target enterprise's technological achievements. Among them, the coordination risk probability is a comprehensive evaluation result, which is obtained by multiplying the absolute difference between the technology maturity level and the market adaptation index by the correlation density.

[0036] Further, to solve the problem of insufficient sensitivity of traditional model market, realize the minute-level response of market fluctuation, and solve the industry pain point of delay of enterprise market response caused by mutation in technology evolution. The embodiment of the application updates the model by adopting a dynamic updating mode of short-term cycle and long-term cycle. Specifically, the enterprise technology achievement evaluation method can also include: updating the preset deep learning algorithm based on a double-cycle dynamic updating mechanism; the double-cycle dynamic updating mechanism includes target short-term cycle updating and target long-term cycle updating, the target short-term cycle updating is a model updating operation triggered based on market fluctuation events; and the target long-term cycle updating is a model updating operation triggered based on technology breakthrough events. That is, the short-term cycle is to fine-tune the market adaptation branch parameters according to market fluctuations; and the long-term cycle is to trigger feature updating and full model retraining of the atlas in the event of a major event such as a technology breakthrough.

[0037] As can be seen from the above, the embodiment of the application accesses multi-source data of technical dimensions such as patents, papers, and R&D data, and market dimensions such as user behavior, industry reports, and competitive intelligence, correlates the dynamic deviation of the technology stage and the market window period through mapping, and solves the problem of data fragmentation by aligning the patent terminology and market concepts through semantics; generates a dynamic technology and market correlation network, taking technology nodes and market nodes as entities, constructs a cross-domain correlation atlas through a cross-domain attention mechanism, and captures the implicit correlation between technology evolution and market demand; based on a multi-task Transformer model, the cross-domain features are extracted through a shared encoder, and the three indexes of intelligent evaluation are output through dynamic weight adjustment, realizing the joint intelligent prediction of technology maturity and market adaptability.

[0038] Referring to Figure 5 The embodiment of the application discloses an enterprise technology achievement evaluation device, which comprises:

[0039] The data acquisition module 11 is configured to acquire multi-source data related to the target enterprise technology achievement, including technical dimension data and market dimension data; The feature fusion module 12 is configured to perform a feature fusion operation on the technical dimension data and the market dimension data by using a preset spatio-temporal alignment engine and a preset semantic alignment engine to obtain a fusion feature vector; the technical dimension data includes patent data, paper data, and R&D data; the market dimension data includes user behavior data, industry report data, and competitive intelligence data; and the fusion feature vector includes a technical feature vector and a market feature vector; The atlas construction module 13 is configured to construct technology nodes and market nodes based on the fusion feature vector, and construct a dynamic correlation network atlas based on the technology nodes and the market nodes by using a cross-domain attention network created based on a bidirectional attention mechanism; the dynamic correlation network atlas is a graph representing the correlation between the technology nodes and the market nodes. The result generation module 14 is used to analyze the dynamic association network map using a preset deep learning algorithm to obtain the target analysis results corresponding to the target enterprise's technological achievements; the target analysis results include the technology maturity level, market adaptation index and coordination risk probability.

[0040] In some specific implementations, the feature fusion module 12 may specifically include: A mapping benchmark offset rule design unit, configured to design a mapping benchmark offset rule from a technology stage to a market window period based on a dynamic offset mechanism using the preset spatiotemporal alignment engine; a data mapping unit, configured to generate a dynamic offset related to the strength of the technology breakthrough using the preset spatiotemporal alignment engine based on a preset compensation algorithm, and map the technology dimension data and the market dimension data onto a unified timeline based on the mapping benchmark offset rule and the dynamic offset, so as to obtain the technology dimension data and the market dimension data after spatiotemporal alignment;

[0041] The fusion feature vector generating unit is used to use the preset semantic alignment engine to adopt a two-way vectorization method to perform a feature fusion operation on the technical dimension data and the market dimension data after the spatiotemporal alignment to obtain a fusion feature vector.

[0042] In some specific embodiments, the map construction module 13 may specifically include: A first node generating unit is configured to deepen the technology feature vector based on an international patent classification tree to obtain a technology node; A second node generating unit is configured to expand the market feature vector based on the industrial chain to obtain a market node; an association relationship building unit, configured to utilize a cross-domain attention network created based on a bidirectional attention mechanism, establish a first association relationship representing the contribution of technology to the market and a second association relationship representing the market's traction on technology based on the technology node and the market node, and calculate a first association strength of the first association relationship and a second association strength of the second association relationship using a preset bidirectional attention mechanism; A dynamic association network graph construction unit is used to construct a dynamic association network graph based on the first association relationship, the second association relationship, the technology node and the market node.

[0043] In some specific implementations, the result generation module 14 may specifically include: An evaluation weight parameter adjustment unit, configured to obtain market volatility monitoring data and adjust the evaluation weight parameters based on the market volatility monitoring data; The target analysis result generating unit is used to analyze the dynamic association network map based on the adjusted evaluation weight parameters using a preset deep learning algorithm to obtain the target analysis results corresponding to the technological achievements of the target enterprise.

[0044] In some specific implementations, the enterprise technology achievement evaluation device may further include: A dynamic association network graph optimization unit is configured to eliminate, based on a preset dynamic maintenance strategy, technology nodes and market nodes whose association closeness is lower than a preset strength threshold or whose association closeness changes by more than a preset change threshold within a preset time, so as to optimize the dynamic association network graph; the association closeness value is a geometric average of the first association strength and the second association strength; A deep learning algorithm update unit is used to update the preset deep learning algorithm based on a dual-loop dynamic update mechanism; the dual-loop dynamic update mechanism includes a target short-term loop update and a target long-term loop update, the target short-term loop update is a model update operation triggered by a market fluctuation event; the target long-term loop update is a model update operation triggered by a technological breakthrough event.

[0045] Furthermore, the embodiment of the present application also discloses an electronic device, Figure 6 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram should not be considered as any limitation on the scope of use of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps of the enterprise technology achievement evaluation method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0046] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device. The communication protocol it follows is any communication protocol that can be applied to the technical solution of this application and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world. Its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0047] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or CD, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0048] The operating system 221 is used to manage and control the various hardware devices and computer programs 222, which can be Windows Server, Netware, Unix, Linux, etc. In addition to the computer programs for implementing the enterprise technology achievement evaluation method disclosed in any of the preceding embodiments, the computer programs 222 can further include computer programs for completing other specific work.

[0049] Further, the present application also discloses a computer readable storage medium for storing a computer program; wherein the computer program is executed by a processor to implement the enterprise technology achievement evaluation method disclosed above. The specific steps of the method can refer to the corresponding content disclosed in the preceding embodiments, which will not be repeated here.

[0050] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts of each embodiment can be referred to each other. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the relevant part can refer to the method part.

[0051] The skilled person can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware, computer software or a combination of the two. In order to clearly show the interchangeability of hardware and software, the composition and steps of each example have been described in the above description. Whether the functions are realized by hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0052] The steps of the method or algorithm described in combination with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the art.

[0053] Finally, it needs to be pointed out that in this document, relational terms such as first and second and the like can only be intended to distinguish one entity or operation from another entity or operation without necessarily requiring or implying any actual such relationship or order between such entities or operations. Moreover, the terms "comprising", "including", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, an element defined by the statement "comprising a" does not exclude the existence of additional identical elements in the process, method, article, or apparatus including the stated element.

[0054] The above detailed description of the technical solutions provided by the present application has been provided, and the principles and implementation modes of the present application have been described by applying specific examples. The above description of the examples is only for the purpose of helping to understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed, and the above description of the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for evaluating enterprise technological achievements, characterized in that: include: Acquire multi-source data related to the target enterprise's technological achievements, including technical and market-related data; Using a preset spatiotemporal alignment engine and a preset semantic alignment engine, a feature fusion operation is performed on the technical dimension data and the market dimension data to obtain a fused feature vector; the technical dimension data includes patent data, paper data, and R&D data; the market dimension data includes user behavior data, industry report data, and competitive intelligence data; the fused feature vector includes a technical feature vector and a market feature vector; Constructing technology nodes and market nodes based on the fused feature vector, utilizing a cross-domain attention network created based on a bidirectional attention mechanism, and constructing a dynamic association network graph based on the technology nodes and the market nodes; The dynamic association network graph is a graph that represents the association between the technology nodes and the market nodes; The dynamic association network map is analyzed using a preset deep learning algorithm to obtain target analysis results corresponding to the target enterprise's technological achievements; the target analysis results include technology maturity level, market adaptation index and coordination risk probability.

2. The enterprise technology achievement evaluation method according to claim 1, characterized in that: The utilizing a preset spatiotemporal alignment engine and a preset semantic alignment engine to perform a feature fusion operation on the technical dimension data and the market dimension data to obtain a fused feature vector includes: Utilizing the preset spatiotemporal alignment engine to design a mapping benchmark offset rule for the technology stage to the market window period based on a dynamic offset mechanism; Utilizing the preset spatiotemporal alignment engine to generate a dynamic offset related to the strength of the technological breakthrough based on a preset compensation algorithm, and mapping the technology dimension data and the market dimension data onto a unified timeline based on the mapping benchmark offset rule and the dynamic offset, so as to obtain the technology dimension data and the market dimension data after spatiotemporal alignment; The preset semantic alignment engine is used to perform feature fusion operation on the technical dimension data and the market dimension data after the spatiotemporal alignment in a two-way vectorization manner to obtain a fused feature vector.

3. The enterprise technology achievement evaluation method according to claim 1, characterized in that: The constructing of technology nodes and market nodes based on the fusion feature vector includes: Deepening the technical feature vector based on the international patent classification tree to obtain a technical node; The market characteristic vector is expanded based on the industrial chain to obtain a market node.

4. The enterprise technology achievement evaluation method according to claim 1, characterized in that: The cross-domain attention network created based on the bidirectional attention mechanism and the dynamic association network map constructed based on the technology nodes and the market nodes include: Using a cross-domain attention network created based on a bidirectional attention mechanism, a first correlation relationship representing the contribution of technology to the market and a second correlation relationship representing the market's influence on technology are established based on the technology node and the market node, and a first correlation strength of the first correlation relationship and a second correlation strength of the second correlation relationship are calculated using a preset bidirectional attention mechanism; A dynamic association network graph is constructed based on the first association relationship, the second association relationship, the technology node, and the market node.

5. The enterprise technology achievement evaluation method according to claim 4, characterized in that: After utilizing the cross-domain attention network created based on the bidirectional attention mechanism and constructing a dynamic association network graph based on the technology nodes and the market nodes, the method further includes: Based on the preset dynamic maintenance strategy, technical nodes and market nodes whose correlation closeness is lower than the preset strength threshold or the change amplitude of the correlation closeness within the preset time is greater than the preset change threshold are eliminated to complete the optimization of the dynamic correlation network map; the value of the correlation closeness is the value obtained by the geometric average of the first correlation strength and the second correlation strength.

6. The enterprise technology achievement evaluation method according to claim 1, characterized in that: The use of a preset deep learning algorithm to analyze the dynamic association network graph to obtain a target analysis result corresponding to the target enterprise's technological achievements includes: Obtaining market volatility monitoring data, and adjusting assessment weight parameters based on the market volatility monitoring data; The dynamic association network map is analyzed using a preset deep learning algorithm based on the adjusted evaluation weight parameters to obtain the target analysis results corresponding to the target enterprise's technological achievements.

7. The enterprise technology achievement evaluation method according to any one of claims 1 to 6, characterized in that: Also includes: Updating the preset deep learning algorithm based on a dual-loop dynamic update mechanism; The dual-cycle dynamic update mechanism includes target short-term cycle update and target long-term cycle update. The target short-term cycle update is a model update operation triggered by market fluctuation events; the target long-term cycle update is a model update operation triggered by technological breakthrough events.

8. An enterprise technology achievement evaluation device, characterized in that: include: A data acquisition module is used to acquire multi-source data related to the target enterprise's technological achievements, including technical dimension data and market dimension data; a feature fusion module, configured to perform a feature fusion operation on the technical dimension data and the market dimension data using a preset spatiotemporal alignment engine and a preset semantic alignment engine to obtain a fused feature vector; the technical dimension data includes patent data, paper data, and R&D data; the market dimension data includes user behavior data, industry report data, and competitive intelligence data; and the fused feature vector includes a technical feature vector and a market feature vector; A graph construction module, configured to construct technology nodes and market nodes based on the fused feature vector, and to construct a dynamic association network graph based on the technology nodes and the market nodes using a cross-domain attention network created based on a bidirectional attention mechanism; The dynamic association network graph is a graph that represents the association between the technology nodes and the market nodes; A result generation module is used to analyze the dynamic association network map using a preset deep learning algorithm to obtain target analysis results corresponding to the target enterprise's technological achievements; the target analysis results include technology maturity level, market adaptation index and coordination risk probability.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the enterprise technological achievement evaluation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that Used to store a computer program, wherein when the computer program is executed by a processor, it implements the enterprise technology achievement evaluation method according to any one of claims 1 to 7.

Images